Kijai

/

WanVideo_comfy

like 284

Why do you always act so quickly every time👍

where to get workflow for i2v 720p ? thanks for your work.

waiting gguf

He is boss💪

waiting gguf

https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main

Thank you very much

Are these models only for ComfyUI? Trying to use them in a Colab with no UI. Replacing original models with these versions (14BT2V) gives lots of errors:

File "/usr/local/lib/python3.11/dist-packages/diffusers/models/modeling_utils.py", line 894, in from_pretrained
raise ValueError(
ValueError: Cannot load <class 'wan.modules.model.WanModel'> from /content/drive/MyDrive/Wan2.1/Wan2.1-T2V-14B because the following keys are missing:
blocks.35.cross_attn.o.bias, blocks.32.self_attn.v.bias, blocks.37.cross_attn.o.weight, blocks.30.self_attn.v.bias, blocks.30.self_attn.v.weight, blocks.39.self_attn.q.weight, blocks.34.cross_attn.v.bias, blocks.34.ffn.0.bias, and so on.. Any help would be appreciated.

Are these models only for ComfyUI? Trying to use them in a Colab with no UI. Replacing original models with these versions (14BT2V) gives lots of errors:

File "/usr/local/lib/python3.11/dist-packages/diffusers/models/modeling_utils.py", line 894, in from_pretrained
raise ValueError(
ValueError: Cannot load <class 'wan.modules.model.WanModel'> from /content/drive/MyDrive/Wan2.1/Wan2.1-T2V-14B because the following keys are missing:
blocks.35.cross_attn.o.bias, blocks.32.self_attn.v.bias, blocks.37.cross_attn.o.weight, blocks.30.self_attn.v.bias, blocks.30.self_attn.v.weight, blocks.39.self_attn.q.weight, blocks.34.cross_attn.v.bias, blocks.34.ffn.0.bias, and so on.. Any help would be appreciated.

I didn't modify the structure of the model at all, it should work if the code just handles single file instead of the original chunked files.